.png){kind=icon}
.png){kind=icon}
Return
A Behavior Tree and Dynamic Motion Primitive-Based Framework for Learning and Executing Robotic Tasks From Demonstration
.png){kind=icon}
PRE
AI
DOI：10.1109/TASE.2026.3663665.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Learning from Demonstrations (LfD) enables robots to acquire complex skills by observing human behavior, significantly reducing the need for explicit programming. However, applying LfD in industrial settings remains challenging due to limited demonstrations, variability in task executions, and the need to generalize across diverse scenarios. To address these issues, this paper presents a learning based hierarchical task and motion planning framework that integrates Behavior Trees (BT) for high-level task sequencing and Dynamic Motion Primitives (DMP) for low-level motion generation. Demonstration trajectories are segmented and actions are generated using an agent-centric, state-augmented segmentation strategy. Subsequently, relevant features are automatically extracted to define the pre- and post-conditions for each action for the construction of a modular BT. For motion execution, DMP are enhanced with a recovery mechanism for adaptive, obstacle-aware reproduction. A backchaining mechanism is also introduced for BT extension. Validation was performed through simulation and real-world experiments on multiple tasks. Comparative results demonstrate that the proposed method outperforms existing LfD and planning baselines in task success rate, efficiency, and motion smoothness, highlighting its potential for flexible and scalable automation. Note to Practitioners—This work presents a learning-based framework that integrates BT and DMP to enable robots to efficiently acquire task sequences and motion skills from demonstration. It addresses the limitations of traditional task planning, which often involves tedious logic design, as well as the constraints of imitation learning methods that are typically limited to simple actions. The proposed approach supports learning from complex demonstrations and adaptive execution in cluttered, dynamic environments. It is suited for complex assembly and multi-object placement tasks, offering a practical and flexible solution for rapid deployment of industrial robots.
Keywords:
Behavior tree
dynamica motion primitives
learning from demonstration
Journal
IF:
6.4
Papers:
4.9K
Citations:
1.6W